[Axe ML] Séminaire Mariia Zameshina
Idir Benouaret
Abstract : "Generative modeling methods can generate images from textual or visual inputs. However, diversity in the generated images persists as a major challenge of the existing approaches.
We address this issue head-on and demonstrating that
- the diversity of a generated batch of images is intrinsically linked to the diversity within the latent variables
- leveraging the geometry of the latent space, we can establish an effective metric for quantifying diversity; and
- employing this insight allows one to achieve a significantly enhanced diversity in image generation beyond the capabilities of traditional random independent sampling.
This advancement is consistent across a variety of generative models, including latent diffusion models and GANs. Additionally, we have integrated our contributions into a widely recognized tool for generative image modeling, ensuring that our improvements are accessible to the broader community.
As a result, this work not only presents a methodological advancement in generative modeling but also significantly broadens the scope of potential applications by enhancing the diversity of generated images
Votes du sondage
Meilleur choix
Pour l'instant, le choix ayant reçu le plus grand nombre de votes est :
- mardi 30 avril 2024 - 15h-16h Télécharger en tant que fichier ical/ics
avec 7 votes.